Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Scale-Covariant and Scale-Invariant Gaussian Derivative Networks Read chapter Read first chapter

2021 | OriginalPaper | Chapter

Learning Linear Assignment Flows for Image Labeling via Exponential Integration

Authors : Alexander Zeilmann, Stefania Petra, Christoph Schnörr

Published in: Scale Space and Variational Methods in Computer Vision

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

We introduce a novel algorithm for estimating optimal parameters of linear assignment flows for image labeling. This flow is determined by the solution of a linear ODE in terms of a high-dimensional integral. A formula of the gradient of the solution with respect to the flow parameters is derived and approximated using Krylov subspace techniques. Riemannian descent in the parameter space enables to determine optimal parameters for a \(512 \times 512\) image in less than 10 s, without the need to backpropagate errors or to solve an adjoint equation. Numerical experiments demonstrate a high generative model expressivity despite the linearity of the assignment flow parametrization.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter On the Correspondence Between Replicator Dynamics and Assignment Flows
next chapter On the Geometric Mechanics of Assignment Flows for Metric Data Labeling
Literature
1.
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. In: OSDI (2016)
2.
Al-Mohy, A.H., Higham, N.J.: Computing the Fréchet derivative of the matrix exponential, with an application to condition number estimation. SIAM J. Matrix Anal. Appl. 30(4), 1639–1657 (2009)CrossRef
3.
4.
Baydin, A., Pearlmutter, B., Radul, A., Siskind, J.: Automatic differentiation in machine learning: a survey. J. Mach. Learn. Res. 18, 1–43 (2018)MathSciNetMATH
5.
Benzi, M., Simoncini, V.: Approximation of functions of large matrices with Kronecker structure. Numerische Mathematik 135(1), 1–26 (2017)MathSciNetCrossRef
6.
Higham, N.J.: Functions of Matrices: Theory and Computation. SIAM, USA (2008)CrossRef
7.
Hochbruck, M., Lubich, C.: On Krylov subspace approximations to the matrix exponential operator. SIAM J. Numer. Anal. 34(5), 1911–1925 (1997)MathSciNetCrossRef
8.
Hühnerbein, R., Savarino, F., Petra, S., Schnörr, C.: Learning adaptive regularization for image labeling using geometric assignment. J. Math. Imaging Vis. 63, 186–215 (2021)MathSciNetCrossRef
9.
Kandolf, P., Koskela, A., Relton, S.D., Schweitzer, M.: Computing low-rank approximations of the Fréchet derivative of a matrix function using Krylov subspace methods. arXiv:​2008.​12926 (2020)
10.
Moler, C., Loan, C.V.: Nineteen dubious ways to compute the exponential of a matrix, twenty-five years later. SIAM Rev. 45(1), 3–49 (2003)MathSciNetCrossRef
11.
Najfeld, I., Havel, T.F.: Derivative of the matrix exponential and their computation. Adv. Appl. Math. 16(3), 321–375 (1995)MathSciNetCrossRef
12.
Niesen, J., Wright, W.M.: Algorithm 919: a Krylov subspace algorithm for evaluating the \(\varphi \)-functions appearing in exponential integrators. ACM Trans. Math. Softw. 38(3), 1–19 (2012)MathSciNetCrossRef
13.
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: NIPS (2019)
14.
15.
16.
17.
Zeilmann, A., Savarino, F., Petra, S., Schnörr, C.: Geometric numerical integration of the assignment flow. Inverse Probl. 36(3), 034003 (2020)MathSciNetCrossRef
18.
Zern, A., Zeilmann, A., Schnörr, C.: assignment flows for data labeling on graphs: convergence and stability. arXiv:​2002.​11571 (20 February 2020)
Metadata
Title
Learning Linear Assignment Flows for Image Labeling via Exponential Integration
Authors
Alexander Zeilmann
Stefania Petra
Christoph Schnörr
Copyright Year
2021
Book
Scale Space and Variational Methods in Computer Vision

Print ISBN: 978-3-030-75548-5

Electronic ISBN: 978-3-030-75549-2

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-75549-2_31

Premium Partner

    Image Credits